© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 17-LLAMASCOPE-RES-131K
    11. 29738
    Prev
    Next
    INDEX
    Explanations

    terms and concepts related to religious doctrines and abominations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     componentName
    -0.07
     Pit
    -0.06
    ảo
    -0.06
     oÄį
    -0.06
    _IMPL
    -0.06
     Interfaces
    -0.06
    WRAPPER
    -0.06
    UCH
    -0.06
    alars
    -0.06
    еÑĢаÑħ
    -0.06
    POSITIVE LOGITS
    alley
    0.07
    lette
    0.07
    ordion
    0.06
    ouve
    0.06
    .useState
    0.06
    _fatal
    0.06
    icare
    0.06
    elman
    0.06
     Rei
    0.06
    pane
    0.06
    Activations Density 0.002%

    No Known Activations